Update app.py

app.py

@@ -9,12 +9,8 @@ from langchain.memory import ConversationBufferMemory as MEM,RedisChatMessageHis
 from langchain.schema import SystemMessage as SM,HumanMessage as HM, AIMessage as AM
 from langchain import hub
 import os
-from llama_cpp import Llama
+import torch
 
-llm1 = Llama.from_pretrained(
-	repo_id="peterpeter8585/deepseek-llm-7b-chat-Q8_0-GGUF",
-	filename="deepseek-llm-7b-chat-q8_0.gguf",
-)
 
 from langchain_core.prompts.chat import ChatPromptTemplate, MessagesPlaceholder
 system = '''Respond to the human as helpfully and accurately as possible. You have access to the following tools:
@@ -93,6 +89,7 @@ class Chatchat(BaseChatModel):
         self.tokenizer = AutoTokenizer.from_pretrained(self.model_name, trust_remote_code=True)
         self.model = AutoModelForCausalLM.from_pretrained(
             self.model_name, trust_remote_code=True)
+        self.model=self
 
 
     def _call(